vnhax
JuliusBrussee / caveman
View on GitHub ↗

Independent review by VNHAX. Not affiliated with or endorsed by the project's authors.

33.2% FEWER INPUT TOKENS (PROJECT)CITED BY ADOBE RESEARCHCAVEMAN 4.0: SIX PARTS30+ AGENTSAPACHE-2.0 LICENSE
Caveman: an AI coding agent that answers tersely and reads compressed tool output
JuliusBrussee / caveman — why many token when few do trick

Caveman: Make Your AI Coding Agent Say Less and Read Less

Shorter answers, smaller inputs, same code.
The caveman voice trims chatty answers while keeping code, commands, paths and error messages exact. Input compression shrinks logs, JSON, CSV and test output before the model reads them, and keeps the originals on disk.

33.2%
Fewer input tokens per session
54 Claude Code runs, 18/18 answers right (project)
63 → 20
Tokens for the same fix
Caveman voice example (project)
1.4–2.4×
Cheaper output
Adobe Research, eight models (cited by README)
HOW IT WORKS

The Six Parts of Caveman 4.0

All are on after install; each has its own switch:

Say less

The caveman voice: answer first, one idea per sentence, payload kept verbatim.

Read less

Compresses logs, JSON, CSV and test output before the model reads them.

Auto

Picks the model and effort for each request. Needs a free account.

Blocks

Reusable scripts for code mode, so agents stop retyping the same helper (pre-release).

Waste fixes

Finds where tokens go and keeps the prompt cache warm while you pause.

Browse

Returns web pages to the agent in compressed form.

Outside Results Cited in the README

WhoResult
Adobe Research (CAVEWOMAN paper)Caveman-style output cut cost 1.4× to 2.4× per model, up to 3×, across eight models and five datasets
Elastic (Elasticsearch Labs)63.6% fewer response tokens in eight live MCP scenarios
JetBrainsNo measurable quality loss (p = 0.82) and 8.5% fewer output tokens on 86 coding tasks

Input Compression by File Type (Project Measurements)

File typeWhole-session saving
CSV55.1%
Logs50.2%
YAML46.2%
Test output27.8%
JSON26.4%
HTML9.9% worse (not compressed yet)
All six together33.2% fewer input tokens
Install

One-Command Install

npx @caveman-ai/cli@latest

Mac, Linux and Windows; needs Node.js 22.13+. It finds your agents and logins, shows what it will change, and asks you to confirm. Afterwards plain claude runs with caveman on. caveman status shows what is enabled.

More Commands:
Only the terse-answer skill:
npx skills add JuliusBrussee/caveman -g
Claude Code plugin:
claude plugin marketplace add JuliusBrussee/caveman && claude plugin install caveman@caveman
Turn one part off:
caveman off browse
Uninstall:
npx -y github:JuliusBrussee/caveman -- --uninstall

Why Your Prompts Are Left Alone

The README cites Adobe Research finding that compressing the user's own prompt makes answers worse. So caveman never rewrites what you type; it shortens what the agent says and what it reads from tools.

When It Saves Less

The project's own table shows HTML input getting slightly worse, and notes that "Be concise" is already a strong baseline on new models. Measure on your own sessions with caveman status and your provider's usage data.

HONEST NOTES

Honest Numbers

Caveats the README itself states:

  • Interim result: The Auto "54% cheaper" figure comes from a half-finished run on 85 tasks.
  • Older measurements: The session compression run dates from August 2026 on an older engine.
  • Pre-release parts: Blocks is a release candidate, Python only, with no sandbox yet.
  • Account for Auto: Only Auto needs an account; without signing in, it is off and nothing is sent for it.
🔒 Runs Locally

Uses your own keys or Claude Pro/Max login on your machine. Originals of compressed files stay on disk.

⚖️ License

Apache-2.0 (per GitHub repository metadata).

📘 Docs

README and INSTALL.md cover 30+ agents, Windows, uninstall and the release notes.

Frequently Asked Questions

Does Caveman change the code my agent writes?

No. The README says code, commands, paths and error messages stay untouched, character for character. Only the conversational text gets shorter.

How do I install Caveman?

Run npx @caveman-ai/cli@latest (Node.js 22.13 or newer). It finds your agents, shows what it will change, and asks you to confirm. If you only want shorter answers, run npx skills add JuliusBrussee/caveman -g instead.

Does Caveman rewrite my prompts?

No. The project says your prompts are never rewritten, because research it cites found that compressing the user's prompt makes answers worse.

Does Caveman send my data anywhere?

It runs on your machine with your own keys or login. The optional Auto model router needs a free account; if you are not signed in, Auto is off and nothing is sent for it. Read the privacy section of the README for details.